False comment analysis method based on convolutional neural network

A convolutional neural network and analysis method technology, applied in biological neural network models, semantic analysis, neural architecture, etc., can solve the problems of high cost and low accuracy, reduce overfitting, improve accuracy, reduce effect used

Pending Publication Date: 2020-07-17
ANHUI UNIV OF SCI & TECH
View PDF2 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Aiming at the problems of high cost and low accuracy in existing false comment detection method

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • False comment analysis method based on convolutional neural network
  • False comment analysis method based on convolutional neural network
  • False comment analysis method based on convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0037] This experiment uses the gold data set of false positive reviews collected by MyleOtt et al. to verify this invention. The data set is divided into two categories: positive comments and negative comments, and each type of comments is divided into real comments and fake comments. The number of data samples of each type is equal, 400, and a total of 1600 hotel reviews are used as data samples. These data samples have two feature labels at the beginning.

[0038] A method for analyzing fake comments based on convolutional neural network, comprising the following steps:

[0039] Execute step 1, first load the sample data set from the specified path, because the number of training sample sets has a direct impact on the experimental results, in this experiment, the data set is randomly divided, 80% of the samples are used as the training set to train the data model, and 20% of the The samples serve as a test set to validate the data model.

[0040] Execute step 2, input the ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a false comment method based on a convolutional neural network, and the method combines a mainstream short text feature mining model, and enables the convolutional neural network to be used for the recognition of false commodity evaluation in the field of short text processing. The method comprises the following steps: firstly, selecting a sample data set, taking 80% of sample data as a training set, and taking 20% of samples as a test set; and inputting the training set into a Word2Vec model to obtain a word vector dimension; and then, through convolution calculation and feature extraction, enabling the output result of the model to have relatively high accuracy in precision, recall rate and f1-score. This indicates the feasibility of applying the convolutional neural network model to false comment recognition.

Description

technical field [0001] The invention relates to the field of machine learning, and more specifically, relates to a method for analyzing false comments based on a convolutional neural network. Background technique [0002] With the development of the Internet, online consumption is becoming more and more routine, and people will use comments as an important reference. Many consumer platforms have set up user feedback mechanisms. However, driven by interests, many merchants will find ways to publish some false reviews. Among the massive reviews, if they cannot make correct judgments, it will affect the consumer experience. And it has a bad influence on the development of e-commerce platform. [0003] Therefore, there is an urgent need for a method to accurately identify fake reviews. Some scholars have searched for many methods, but the results are not ideal and the accuracy rate is relatively low. Convolutional neural network has good fault tolerance, parallel processing ab...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06F40/30G06F40/279G06N3/04G06Q30/02
CPCG06Q30/0201G06Q30/0203G06N3/045
Inventor 宋丹陆奎吴杰胜刘洋戴旭凡
Owner ANHUI UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap